skills/t0ugh/videoclaw/video-config/Gen Agent Trust Hub

video-config

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends using uvx videoclaw, which downloads and executes the videoclaw package from an external package registry.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands via the videoclaw CLI to manage project and global configurations.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by processing configuration data which could be influenced by untrusted project files.
  • Ingestion points: The agent reads configuration values using videoclaw config --get and videoclaw config --list.
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded commands within configuration values are present.
  • Capability inventory: The skill possesses shell command execution capabilities through the videoclaw tool.
  • Sanitization: There is no evidence of sanitization or validation of the retrieved configuration values before they are used in the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 10:13 AM